How to use vogent/Vogent-Turn-80M with Transformers:
# Load model directly from transformers import WhisperSmolLMClassifier model = WhisperSmolLMClassifier.from_pretrained("vogent/Vogent-Turn-80M", dtype="auto")
Due to the small size, would we be able to run the model in ONNX on a WebGPU?
· Sign up or log in to comment
